Skip to main content

ORIGINAL RESEARCH article

Front. Pharmacol.
Sec. Experimental Pharmacology and Drug Discovery
Volume 16 - 2025 | doi: 10.3389/fphar.2025.1454029

Prediction of traditional Chinese medicine against diabetes based on multi-source ensemble method

Provisionally accepted
Bin Yang Bin Yang 1,2*Qingyun Chi Qingyun Chi 2*Xiang Li Xiang Li 3*Jinglong Wang Jinglong Wang 4*
  • 1 Zaozhuang University, Zaozhuang, China
  • 2 College of Information Science and Engineering, Zaozhuang University, Zaozhuang, Shandong, China
  • 3 Qingdao Eighth People's Hospital, Qingdao, Shandong Province, China
  • 4 College of Food Science and Pharmaceutical Engineering, Zaozhuang University, Zaozhuang, Shandong Province, China

The final, formatted version of the article will be published soon.

    Traditional Chinese medicine (TCM) prescriptions are generally formulated by the experienced TCM researchers based on their experience and data statistical methods. In order to predict traditional Chinese medicine (TCM) formulas against diabetes more accurately, this paper proposes a novel multi-source ensemble prediction method based on machine learning methods ensemble and multi-source data ensemble. In the method, the multi-source data contain the dataset based on components and the datasets based on targets (DPP-4 and GLP-1). Gradient Boosting Decision Tree (GBDT), flexible neural tree (FNT) and Light Gradient Boosting Machine (lightGBM) are trained with these two kinds of datasets, respectively. As the testing data the compound dataset from TCSMP database is predicted to screen the active ingredients. The frequencies of occurrences of medicinal herbs corresponding to these three algorithms are obtained, respectively, which contain the active ingredient list. Finally, the frequencies of occurrences of the medicinal herbs obtained from the three algorithms with two kinds of datasets are integrated to select the duplicate drugs as the candidate ones for diabetes treatment. The identification results reveal that the proposed ensemble method has the higher accuracy than GBDT, FNT and lightGBM. The medicinal herbs predicted contain Lycii Fructus, Amygdalus Communis Vas, Chrysanthemi Flos, Hippophae Fructus, Mori Follum, Croci Stigma, Maydis Seigma, Ephedra Herba, Cimicifugae Rhizoma, licorice and Epimrdii Herba, which have been proved to have treatment effect on diabetes. The results of network pharmacology show that Myrrha can play a role in treating diabetes through multiple-target and multiple-pathway.

    Keywords: diabetes, Multi-source, Traditional Chinese Medicine Formulas, ensemble, Medicinal herbs

    Received: 24 Jun 2024; Accepted: 03 Jan 2025.

    Copyright: © 2025 Yang, Chi, Li and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Bin Yang, Zaozhuang University, Zaozhuang, China
    Qingyun Chi, College of Information Science and Engineering, Zaozhuang University, Zaozhuang, Shandong, China
    Xiang Li, Qingdao Eighth People's Hospital, Qingdao, Shandong Province, China
    Jinglong Wang, College of Food Science and Pharmaceutical Engineering, Zaozhuang University, Zaozhuang, 277160, Shandong Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.